# Russian Image-Text Retrieval Embdding with CLIP
*author: David Wang*
< br / >
## Description
This operator extracts features for image or text with [CLIP ](https://arxiv.org/abs/2103.00020 ) which can generate embeddings for text and image by jointly training an image encoder and text encoder to maximize the cosine similarity. This is a Russian version of CLIP adopted from [ai-forever/ru-clip ](https://github.com/ai-forever/ru-clip ).
< br / >
## Code Example
Load an image from path './teddy.jpg' to generate an image embedding.
Read the text 'Плюшевый мишка на скейтборде на Таймс-сквер.' to generate an text embedding.
*Write the pipeline in simplified style* :
```python
import towhee
towhee.glob('./teddy.jpg') \
.image_decode() \
.image_text_embedding.ru_clip(model_name='ruclip-vit-base-patch32-224', modality='image') \
.show()
towhee.dc(["'Плюшевый мишка на скейтборде на Таймс-сквер."]) \
.image_text_embedding.ru_clip(model_name='ruclip-vit-base-patch32-224', modality='text') \
.show()
```
< img src = "./vec1.png" alt = "result1" style = "height:20px;" / >
< img src = "./vec2.png" alt = "result2" style = "height:20px;" / >
*Write a same pipeline with explicit inputs/outputs name specifications:*
```python
import towhee
towhee.glob['path']('./teddy.jpg') \
.image_decode['path', 'img']() \
.image_text_embedding.ru_clip['img', 'vec'](model_name='ruclip-vit-base-patch32-224', modality='image') \
.select['img', 'vec']() \
.show()
towhee.dc['text'](["Плюшевый мишка на скейтборде на Таймс-сквер."]) \
.image_text_embedding.ru_clip['text','vec'](model_name='ruclip-vit-base-patch32-224', modality='text') \
.select['text', 'vec']() \
.show()
```
< img src = "./tabular1.png" alt = "result1" style = "height:60px;" / >
< img src = "./tabular2.png" alt = "result2" style = "height:60px;" / >
< br / >
## Factory Constructor
Create the operator via the following factory method
***ru_clip(model_name, modality)***
**Parameters:**
** *model_name:*** *str*
The model name of CLIP. Supported model names:
- ruclip-vit-base-patch32-224
- ruclip-vit-base-patch16-224
- ruclip-vit-large-patch14-224
- ruclip-vit-large-patch14-336
- ruclip-vit-base-patch32-384
- ruclip-vit-base-patch16-384
** *modality:*** *str*
Which modality(*image* or *text* ) is used to generate the embedding.
< br / >
## Interface
An image-text embedding operator takes a [towhee image ](link/to/towhee/image/api/doc ) or string as input and generate an embedding in ndarray.
**Parameters:**
** *data:*** *towhee.types.Image (a sub-class of numpy.ndarray)* or *str*
The data (image or text based on specified modality) to generate embedding.
**Returns:** *numpy.ndarray*
The data embedding extracted by model.
